A Hybrid Force-Position Strategy for Shape Control of Deformable Linear Objects With Graph Attention Networks

TL;DR

This paper introduces a hybrid control strategy combining force and position data, utilizing Graph Attention Networks to improve shape control of deformable linear objects in simulations and real-world tests.

Contribution

It presents a novel hybrid force-position control framework with a graph-based dynamics model for better DLO shape manipulation.

Findings

Effective shape control in simulations and real-world experiments

Enhanced prediction accuracy with graph attention networks

Stable and efficient DLO manipulation demonstrated

Abstract

Manipulating deformable linear objects (DLOs) such as wires and cables is crucial in various applications like electronics assembly and medical surgeries. However, it faces challenges due to DLOs' infinite degrees of freedom, complex nonlinear dynamics, and the underactuated nature of the system. To address these issues, this paper proposes a hybrid force-position strategy for DLO shape control. The framework, combining both force and position representations of DLO, integrates state trajectory planning in the force space and Model Predictive Control (MPC) in the position space. We present a dynamics model with an explicit action encoder, a property extractor and a graph processor based on Graph Attention Networks. The model is used in the MPC to enhance prediction accuracy. Results from both simulations and real-world experiments demonstrate the effectiveness of our approach in achieving efficient and stable shape control of DLOs. Codes and videos are available at https://sites.google.com/view/dlom.